Year: 2025
Type: article
Abstract: A data-driven predictive modelling approach is adopted to a polymetallic uranium deposit at Rohil, Rajasthan state, India through impetus of 3D spatial variability and artificial neural networks (ANN). The present study is a novel attempt to understand whether uranium as an unknown variable can be predicted from the other seven geovariables through a mathematical or machine learning approach. The results of ANN (coefficient of determination R 2 = 0.81) provide better model than multivariate regression models for prediction of uranium. This indicates that neural network design is proper and input variables are suitable for prediction model through machine learning. The present study implies that ANN can be successfully attempted for similar predictive modelling on analogous geochemical data in complex geological set up worldwide.
Authors: Ajoy K. Padhi, Dheeraj Pande
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,790
OpenAlex ID: W4414377775